ModelTC/LightTTS
LightTTS is a lightweight TTS inference framework optimized for CosyVoice2 and CosyVoice3, enabling fast and scalable speech synthesis in Python and supports stream and bistream modes.
LightTTS is a powerful toolkit for converting written text into natural-sounding speech. It takes your text input and, optionally, a short audio sample to match a speaker's voice, then quickly generates high-quality speech audio. This is ideal for developers creating applications that need to generate speech efficiently, such as voice assistants, audiobooks, or interactive communication systems.
Use this if you need a high-performance text-to-speech solution that can rapidly generate spoken audio, especially for services requiring real-time or streaming capabilities.
Not ideal if you are an end-user looking for a ready-to-use application with a graphical interface for personal use.
Stars
31
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ModelTC/LightTTS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
herimor/voxtream
VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control
EveryVoiceTTS/EveryVoice
The EveryVoice TTS Toolkit - Text To Speech for your language
thorstenMueller/Thorsten-Voice
Thorsten-Voice: A free to use, offline working, high quality german TTS voice should be...
daswer123/xtts-webui
Webui for using XTTS and for finetuning it
kadirnar/VoiceHub
VoiceHub: A Unified Inference Interface for TTS Models